BUG: manage raw ods file without cell cache (#55219)

* BUG: manage raw ods file without cell cache * fixup! BUG: manage raw ods file without cell cache
pandas-dev · Sep 20, 2023 · 8371d18 · 8371d18
1 parent c4efa92
commit 8371d18
Show file tree

Hide file tree

Showing 4 changed files with 13 additions and 11 deletions.
diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst
@@ -223,6 +223,7 @@ Bug fixes
 - Bug in :class:`AbstractHolidayCalendar` where timezone data was not propagated when computing holiday observances (:issue:`54580`)
 - Bug in :class:`pandas.core.window.Rolling` where duplicate datetimelike indexes are treated as consecutive rather than equal with ``closed='left'`` and ``closed='neither'`` (:issue:`20712`)
 - Bug in :meth:`DataFrame.apply` where passing ``raw=True`` ignored ``args`` passed to the applied function (:issue:`55009`)
+- Bug in :meth:`pandas.read_excel` with a ODS file without cached formatted cell for float values (:issue:`55219`)
 
 Categorical
 ^^^^^^^^^^^

diff --git a/pandas/io/excel/_odfreader.py b/pandas/io/excel/_odfreader.py
@@ -150,7 +150,7 @@ def get_sheet_data(
                 max_row_len = len(table_row)
 
             row_repeat = self._get_row_repeat(sheet_row)
-            if self._is_empty_row(sheet_row):
+            if len(table_row) == 0:
                 empty_rows += row_repeat
             else:
                 # add blank rows to our table
@@ -182,16 +182,6 @@ def _get_column_repeat(self, cell) -> int:
 
         return int(cell.attributes.get((TABLENS, "number-columns-repeated"), 1))
 
-    def _is_empty_row(self, row) -> bool:
-        """
-        Helper function to find empty rows
-        """
-        for column in row.childNodes:
-            if len(column.childNodes) > 0:
-                return False
-
-        return True
-
     def _get_cell_value(self, cell) -> Scalar | NaTType:
         from odf.namespaces import OFFICENS
 

diff --git a/pandas/tests/io/data/excel/test_unempty_cells.ods b/pandas/tests/io/data/excel/test_unempty_cells.ods
diff --git a/pandas/tests/io/excel/test_odf.py b/pandas/tests/io/excel/test_odf.py
@@ -48,3 +48,14 @@ def test_read_newlines_between_xml_elements_table():
     result = pd.read_excel("test_newlines.ods")
 
     tm.assert_frame_equal(result, expected)
+
+
+def test_read_unempty_cells():
+    expected = pd.DataFrame(
+        [1, np.nan, 3, np.nan, 5],
+        columns=["Column 1"],
+    )
+
+    result = pd.read_excel("test_unempty_cells.ods")
+
+    tm.assert_frame_equal(result, expected)